© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 10555
    Prev
    Next
    INDEX
    Explanations

    presence of the word "checked," indicating it detects whether items are selected or marked as checked

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ViewFeatures
    -0.74
    ]='\
    -0.63
    Vorlage
    -0.57
    
    -0.57
    OrEqualTo
    -0.56
     surla
    -0.56
    MemoryWarning
    -0.54
    Universe
    -0.54
    ArgsConstructor
    -0.53
     Illuminate
    -0.53
    POSITIVE LOGITS
    checked
    2.19
    Checked
    1.99
    CHECKED
    1.15
    isChecked
    1.12
     isChecked
    0.97
    unchecked
    0.94
    setChecked
    0.88
     unchecked
    0.84
     Checked
    0.83
    Unchecked
    0.80
    Activations Density 0.003%

    No Known Activations